AI-Native Product Architecture
Designing a system around a component that can be wrong
A product with a probabilistic component needs bounded uncertainty, reversible actions, visible confidence, honest escalation and a per-interaction economic model, and the interaction shape decides all of them.
Most AI features fail for reasons that have nothing to do with the model. They fail because nobody decided whether the system suggests, drafts or acts, and so nobody designed the undo, the abstention, the escalation or the cost ceiling that each of those shapes implies. This book makes the interaction shape the first decision and derives the rest from it: reversibility, confidence display, routing, unit economics, latency budgets, caching that cannot serve a wrong answer faster, and the evidence that tells you to cut the feature.
What it makes operable
-
01
Choose between suggest, draft and act before designing anything else
-
02
Design reversibility, abstention and escalation into the product surface
-
03
Model the unit economics of one interaction, including its failures
-
04
Decide on evidence when to cut the feature
Contents
12 of 12 published
Every chapter is free to read in the browser, cites its own sources, and stands on its own if you came for one decision rather than the whole argument.
- 01 A Component That Can Be Wrong What a probabilistic dependency does to everything downstream of it. 10 min
- 02 Deciding Where AI Belongs and Where It Does Not A test for whether the model is load-bearing or decorative. 11 min
- 03 Suggest, Draft, or Act: Choosing the Interaction Shape The one decision that fixes reversibility, latency and cost for everything after. 10 min
- 04 Designing Reversibility Into the Product Undo, preview and staging as product features rather than engineering afterthoughts. 11 min
- 05 Confidence, Abstention, and Escalation Letting the product decline, and making a decline useful to whoever reads it. 12 min
- 06 Routing: Capability, Cost, Fallback A routing table derived from per-step eval results rather than from instinct. 12 min
- 07 The Unit Economics of a Feature Cost per successful interaction, counting retries, review and failure. 12 min
- 08 Latency Budgets and Perceived Speed Streaming, optimistic state, and the gap between fast and feeling fast. 12 min
- 09 Caching Without Serving the Wrong Answer Faster Cache identity that includes the principal, the policy and the corpus revision. 12 min
- 10 Data Flywheels That Do Not Poison Themselves Feedback loops that improve the system instead of laundering its errors. 13 min
- 11 Failure UX: What the User Sees When It Is Wrong Designing the wrong answer, because you are going to ship one. 12 min
- 12 Deciding to Cut the Feature The evidence and the threshold for stopping without a political fight. 12 min
Evidence · 3 sources
Third-party sources behind the book's premise. Every figure in them belongs to the party that published it and is attributed to them in the text.
